cs-wiki-librarian

Dispatched sub-agent that answers queries against an LLM Wiki vault. Reads index.md first, drills into 3-10 relevant pages across categories, synthesizes an answer with inline [[wikilink]] citations, and offers to file the answer back into the wiki as a new comparison or synthesis page. Spawn when the user asks a substantive question the wiki might answer, says "what does the wiki say about X", "compare A and B across my sources", or wants to explore a topic.

Quality

72%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

Securityby

Passed

No findings from the security scan

Fix and improve this skill with Tessl

tessl review fix ./.gemini/skills/cs-wiki-librarian/SKILL.md

Quality

Content

65%Weight 40%Scale 1-5

Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.

The body is concise and largely actionable with real commands and a clear answer format, and the workflow is well-sequenced for reading. The main weaknesses are the missing validation checkpoint before vault-mutating write operations and external references whose structure cannot be verified within this skill's bundle.

Suggestions

Add an explicit validation checkpoint before filing an answer back into the vault (e.g., verify the new page against the chosen template and confirm index.md was updated), to lift workflow_clarity above the destructive/batch cap of 3.

Resolve the '<plugin>' placeholder in the example commands so they are copy-paste ready, or document how the agent should resolve the plugin path.

Surface the external reference files (query-workflow.md, page-formats.md) with clearer one-level-deep navigation signaling, or pull the most critical workflow detail inline so the body is self-contained.

Dimension	Reasoning	Score
Conciseness	Lean and assumes Claude's competence ('The wiki has done the hard work', 'They're short and curated') with no padding about what a wiki is; a few short explanatory asides ('This is the compounding move') could be trimmed but overall efficient.	4 / 5
Actionability	Provides concrete, mostly-executable guidance including real command lines (the wiki_search.py and append_log.py invocations) and a concrete answer format; minor gaps such as the '<plugin>' placeholder leave a step unresolved for the agent.	4 / 5
Workflow Clarity	Steps are clearly sequenced (read index → read pages → follow links → search → synthesize → file back), but filing back is a write/batch operation with no validation checkpoint before mutating the vault, which caps clarity per the destructive/batch rule.	3 / 5
Progressive Disclosure	Body points to reference files (query-workflow.md, page-formats.md) for detail, but those references live outside this skill's bundle (the llm-wiki skill's references dir) and are not clearly signaled as one-level-deep, and no bundle files exist here to confirm structure.	3 / 5
	Total	14 / 20 Passed

Description

80%Weight 40%Scale 1-5

Based on the skill's description, can an agent find and select it at the right time? Clear, specific descriptions lead to better discovery.

A strong, specific description that clearly states both what the sub-agent does and when to spawn it, with natural trigger phrases drawn from likely user utterances. It is comprehensive on capabilities and largely distinct, held back only by slightly bundled trigger phrasing and a few missing synonyms.

Dimension	Reasoning	Score
Specificity	Lists multiple concrete actions — 'Reads index.md first, drills into 3-10 relevant pages across categories, synthesizes an answer with inline [[wikilink]] citations, and offers to file the answer back into the wiki as a new comparison or synthesis page' — with comprehensive coverage.	5 / 5
Completeness	Clearly answers both 'what' (the reading/drilling/synthesizing/filing actions) and 'when' (explicit 'Spawn when...' triggers); the 'when' clause is concrete but bundles multiple triggers into one sentence.	4 / 5
Trigger Term Quality	Includes natural phrases users would say ('what does the wiki say about X', 'compare A and B across my sources', 'explore a topic'); a few common synonyms are missing but coverage is strong.	4 / 5
Distinctiveness Conflict Risk	Niche is clear — answering against an LLM Wiki vault — with distinct 'wiki'/'vault'/'[[wikilink]]' triggers; minor overlap risk with general research skills, but the filing-back step sets it apart.	4 / 5
	Total	17 / 20 Passed

Validation

93%

Warnings & errors only

Checks the skill against the spec for correct structure and formatting. All validation checks must pass before discovery and implementation can be scored.

Validation — 15 / 16 Passed

Validation for skill structure

Criteria	Description	Result
frontmatter_unknown_keys	Unknown frontmatter key(s) found; consider removing or moving to metadata	Warning

	Total	15 / 16 Passed

Repository: alirezarezvani/claude-skills
Path: .gemini/skills/cs-wiki-librarian/SKILL.md
Commit: 19392f7

Reviewed: ~5 hours ago

Table of Contents

Discovery Implementation Validation

Is this your skill?

If you maintain this skill, you can claim it as your own. Once claimed, you can manage eval scenarios, bundle related skills, attach documentation or rules, and ensure cross-agent compatibility.